Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
22,592 documents
This Chinese-language post proposes a stock screen combining daily price range, an estimate of prior-day major-investor control based on money flow, and association with the metaverse theme. It describes the approach as using both technical and fundamental…
This Chinese stock screening note proposes selecting shares with MACD above zero, a specified company concept, and a reported ownership concentration ratio above 21%. Its stated rationale is that positive MACD may indicate upward momentum, while the company…
The document introduces reinforcement learning through the interaction of an agent and an environment, where actions produce feedback and the objective is to maximize discounted future rewards. It frames the problem as a Markov decision process, explaining…
This short-term A-share screen combines three conditions: RSI below 65, parent-attributable net profit growth above 20% and no more than 100%, and a positive daily MACD reading. The document presents RSI as a way to find stocks that may have rebound…
This A-share screening rule combines a turnover range of 3% to 12%, a rising DEA signal, and a close above the previous session’s low. The document explains the turnover filter as a way to focus on actively traded stocks and treats rising DEA and the price…
A BigQuant forum question asks how to select the ten stocks with the strongest return over the previous calendar year on the first trading day of a new year. The user’s current approximation compares prices about 250 trading days apart, but they want a…
This document describes a Chinese equity screen for stocks classified in the metaverse theme. It selects shares trading above their five-day moving average and where the KDJ indicator has just formed a bullish cross. The proposed logic combines a thematic…
A BigQuant forum exchange discusses why feature extraction can return multiple records for a stock on a given day, even when one record is expected. The suggested cause is that the feature input stage reads across tables; joining data with multiple matching…
This brief introduction contrasts linear regression of factor data with decision trees. Its central point is that market returns may not relate to factors in a simple linear way, so a tree-based method is worth considering when studying how factors…
This report presents an A-share stock-selection framework that applies StockRanker, a gradient-boosted learning-to-rank model, to fundamental, financial, and trading factors. It tests 282 individual factors across short, medium, and long holding horizons,…
This Chinese-language post describes a technical stock screen for mainland China equities. It looks for stocks with daily price amplitude above 1, trading volume above 10,000 lots, an open above the prior close, and a Force Index condition intended to…
The XBody strategy is a daily, rule-based system presented for stocks, indices, and forex, with parameters optimized by its author on the CAC index. It calculates candle body size as close minus open, then takes the change in that value over time and sums it…
This stock screen selects for daily price amplitude of at least one percent, a volume ratio between 1.5 and 6 relative to a five-day average, and positive weekly price bars. The article frames the amplitude condition as a way to focus on more active stocks,…
This stock-screening approach combines three technical conditions: amplitude above a threshold, a rising sequence of price lows, and a MACD signal above its zero line. The document describes the idea as a way to find volatile stocks whose price structure is…
The document summarizes two ways to classify crowded equity holdings. For passive crowding, it first divides stocks into size groups using market-capitalization thresholds, then ranks them within each group by the rolling change in passive-fund ownership as…
The document explains how to adapt a StockRanker multi-factor stock-selection workflow to Hong Kong and US equities on BigQuant. The backtest uses BigTrader’s custom historical data input, which must include date, instrument, and daily open, high, low,…
This document describes a Chinese equity screening rule that combines daily price range, turnover, and a prior-day indicator intended to represent dominant capital control. The stated thresholds are an amplitude above 1 and turnover above 2% but no more than…
This report reviews Chinese market and exchange-traded product developments for the week of March 30 to April 3, 2020. It summarizes moves in domestic equity indexes, bond yields, precious metals, currencies, and traded ETP categories. Equity and…
This Chinese-language post outlines a short-term stock selection screen. It looks for stocks with at least five overlapping moving averages, a positive but below 35% return over ten days, and a shortening MACD histogram below zero on a 15-minute chart. The…
The document presents a basic stock selection screen combining positive MACD, upward movement in short moving averages, and a share price below 12 yuan. It interprets positive MACD as a sign of an upward state and rising averages as evidence of trend…
This stock selection rule combines three daily conditions: price range exceeds 1%, the KDJ indicator has just formed a bullish crossover, and the day’s high matches the highest high over the current and previous day. The article presents the combination as a…
This stock-screening note proposes selecting companies in the metaverse sector whose latest price return is positive and whose stated circulating share count is at or below a specified threshold. It explains that free-float shares describe stock available…
This Chinese stock-selection post proposes combining daily price amplitude, a ranking based on net large-order volume, and a candlestick pattern described as a morning star. It presents these conditions as a way to find active stocks with short-term momentum…
This research summary compares common stock-selection factors in the U.S. and Chinese markets, with a test of seven factor groups and 24 signals in the Russell 3000 universe. It reports that profitability, valuation, and growth measures were among the…